Nava
Overview
Be Challenged and Make a Difference In a world of technology, people make the difference. We believe if we invest in great people, then great things will happen. At AnaVation, we provide unmatched value to our customers and employees through innovative solutions and an engaging culture. Description of Task to be Performed: AnaVation is seeking a Senior Agentic-AI Software engineer to join our team. The role involves designing, developing, and deploying advanced agentic AI systems that autonomously perform complex tasks, make decisions, and interact with dynamic environments. You will collaborate with cross-functional teams to deliver scalable, efficient, and ethical AI solutions that drive business impact. You will architect and implement agentic AI systems capable of autonomous decision-making, task planning, and execution in real-world applications. Design and integrate multi-agent systems to solve complex problems through collaborative and competitive interactions. Develop and fine-tune large language models (LLMs) and reinforcement learning (RL) models to power agentic behaviors. Implement robust APIs and interfaces to integrate AI agents with external systems, databases, and tools. Optimize AI models for performance, scalability, and low-latency inference in production environments. Conduct rigorous testing, validation, and monitoring of AI agents to ensure reliability, safety, and alignment with ethical standards. Collaborate with product managers, data scientists, and software engineers to define requirements and deliver end-to-end AI solutions. Stay updated on the latest advancements in agentic AI, LLMs, and RL, and incorporate cutting-edge techniques into development workflows. Mentor junior developers and contribute to knowledge-sharing within the team. Responsibilities
Design, develop, and deploy agentic AI systems with autonomous decision-making and task execution in real-world environments. Architect and implement multi-agent systems enabling collaborative and competitive interactions. Develop and fine-tune large language models (LLMs) and reinforcement learning (RL) models for agentic behaviors. Implement robust APIs and interfaces to integrate AI agents with external systems, databases, and tools. Optimize models for performance, scalability, and low-latency inference in production. Conduct rigorous testing, validation, and monitoring to ensure reliability, safety, and ethical alignment. Collaborate with product managers, data scientists, and software engineers to define requirements and deliver end-to-end AI solutions. Stay current with advancements in Agentic AI, LLMs, and RL, and incorporate new techniques into workflows. Mentor junior developers and contribute to knowledge sharing within the team. Required Qualifications
Clearance: Active TS/SCI within the last 24 months Education: BA/BS in Computer Science or related field Experience: BS + 10 years or MS + 8 years in computer science, AI, machine learning, or related field 5+ years of experience in AI/ML development, with at least 2 years focused on agentic AI or autonomous systems Proven track record of deploying production-grade AI systems, including experience with AWS Bedrock Strong problem-solving skills and ability to work in a fast-paced, collaborative environment Preferred Qualifications
PhD in computer science, AI, machine learning, or related field Technology Stack: Programming Languages: Python (primary), JavaScript/TypeScript (for API development), C++ (for performance-critical components) Frameworks and Libraries: Machine Learning: PyTorch, TensorFlow, JAX Reinforcement Learning: Stable-Baselines3, Ray RLlib, OpenAI Gym, or Gymnasium Agentic AI Frameworks: LangChain, LlamaIndex, AutoGen, or CrewAI API Development: FastAPI, Flask, or Node.js Cloud Platforms: AWS (SageMaker, Lambda, Bedrock), Google Cloud AI, Azure AI Containerization: Docker, Kubernetes Version Control: Git, GitHub, or GitLab Databases: SQL (PostgreSQL, MySQL), NoSQL (MongoDB, DynamoDB) DevOps Tools: CI/CD pipelines (Jenkins, GitHub Actions), monitoring tools (Prometheus, Grafana) AI Models and Techniques: Large Language Models (LLMs): Experience with models like LLaMA, GPT, BERT, or Grok for NLU/NLG, including deploying and managing LLMs on AWS Bedrock Reinforcement Learning (RL): Expertise in RL algorithms (e.g., DQN, PPO, SAC) and multi-agent RL systems Agentic AI Paradigms: Knowledge of goal-driven agents, task decomposition, and autonomous planning (e.g., ReAct, Plan- and-Execute architectures) Prompt Engineering: Designing prompts for LLMs to achieve reliable outputs, optimized for Bedrock model ecosystem Model Fine-Tuning: Techniques like LoRA, QLoRA, or full fine-tuning for domain-specific applications, with experience using Bedrock for fine-tuning workflows Evaluation Metrics: Familiarity with BLEU, ROUGE, perplexity, and custom metrics for agent performance Benefits
Generous cost sharing for medical insurance for the employee and dependents 100% company paid dental insurance for employees and dependents 100% company paid long-term and short-term disability insurance 100% company paid vision insurance for employees and dependents 401k plan with generous match and 100% immediate vesting Competitive Pay Generous paid leave and holiday package Tuition and training reimbursement Life and AD&D Insurance About AnaVation
AnaVation is the leader in solving the most complex technical challenges for collection and processing in the U.S. Federal Intelligence Community. We are a US owned company headquartered in Chantilly, Virginia. We deliver groundbreaking research with advanced software and systems engineering that provides an information advantage to contribute to the mission and operational success of our customers. We offer complex challenges, a top-notch work environment, and a world-class, collaborative team. If you want to grow your career and make a difference while doing it, AnaVation is the perfect fit for you! AnaVation is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to sex, race, color, religion, national origin, disability, protected Veteran status, age, or any other characteristic protected by law.
#J-18808-Ljbffr
Be Challenged and Make a Difference In a world of technology, people make the difference. We believe if we invest in great people, then great things will happen. At AnaVation, we provide unmatched value to our customers and employees through innovative solutions and an engaging culture. Description of Task to be Performed: AnaVation is seeking a Senior Agentic-AI Software engineer to join our team. The role involves designing, developing, and deploying advanced agentic AI systems that autonomously perform complex tasks, make decisions, and interact with dynamic environments. You will collaborate with cross-functional teams to deliver scalable, efficient, and ethical AI solutions that drive business impact. You will architect and implement agentic AI systems capable of autonomous decision-making, task planning, and execution in real-world applications. Design and integrate multi-agent systems to solve complex problems through collaborative and competitive interactions. Develop and fine-tune large language models (LLMs) and reinforcement learning (RL) models to power agentic behaviors. Implement robust APIs and interfaces to integrate AI agents with external systems, databases, and tools. Optimize AI models for performance, scalability, and low-latency inference in production environments. Conduct rigorous testing, validation, and monitoring of AI agents to ensure reliability, safety, and alignment with ethical standards. Collaborate with product managers, data scientists, and software engineers to define requirements and deliver end-to-end AI solutions. Stay updated on the latest advancements in agentic AI, LLMs, and RL, and incorporate cutting-edge techniques into development workflows. Mentor junior developers and contribute to knowledge-sharing within the team. Responsibilities
Design, develop, and deploy agentic AI systems with autonomous decision-making and task execution in real-world environments. Architect and implement multi-agent systems enabling collaborative and competitive interactions. Develop and fine-tune large language models (LLMs) and reinforcement learning (RL) models for agentic behaviors. Implement robust APIs and interfaces to integrate AI agents with external systems, databases, and tools. Optimize models for performance, scalability, and low-latency inference in production. Conduct rigorous testing, validation, and monitoring to ensure reliability, safety, and ethical alignment. Collaborate with product managers, data scientists, and software engineers to define requirements and deliver end-to-end AI solutions. Stay current with advancements in Agentic AI, LLMs, and RL, and incorporate new techniques into workflows. Mentor junior developers and contribute to knowledge sharing within the team. Required Qualifications
Clearance: Active TS/SCI within the last 24 months Education: BA/BS in Computer Science or related field Experience: BS + 10 years or MS + 8 years in computer science, AI, machine learning, or related field 5+ years of experience in AI/ML development, with at least 2 years focused on agentic AI or autonomous systems Proven track record of deploying production-grade AI systems, including experience with AWS Bedrock Strong problem-solving skills and ability to work in a fast-paced, collaborative environment Preferred Qualifications
PhD in computer science, AI, machine learning, or related field Technology Stack: Programming Languages: Python (primary), JavaScript/TypeScript (for API development), C++ (for performance-critical components) Frameworks and Libraries: Machine Learning: PyTorch, TensorFlow, JAX Reinforcement Learning: Stable-Baselines3, Ray RLlib, OpenAI Gym, or Gymnasium Agentic AI Frameworks: LangChain, LlamaIndex, AutoGen, or CrewAI API Development: FastAPI, Flask, or Node.js Cloud Platforms: AWS (SageMaker, Lambda, Bedrock), Google Cloud AI, Azure AI Containerization: Docker, Kubernetes Version Control: Git, GitHub, or GitLab Databases: SQL (PostgreSQL, MySQL), NoSQL (MongoDB, DynamoDB) DevOps Tools: CI/CD pipelines (Jenkins, GitHub Actions), monitoring tools (Prometheus, Grafana) AI Models and Techniques: Large Language Models (LLMs): Experience with models like LLaMA, GPT, BERT, or Grok for NLU/NLG, including deploying and managing LLMs on AWS Bedrock Reinforcement Learning (RL): Expertise in RL algorithms (e.g., DQN, PPO, SAC) and multi-agent RL systems Agentic AI Paradigms: Knowledge of goal-driven agents, task decomposition, and autonomous planning (e.g., ReAct, Plan- and-Execute architectures) Prompt Engineering: Designing prompts for LLMs to achieve reliable outputs, optimized for Bedrock model ecosystem Model Fine-Tuning: Techniques like LoRA, QLoRA, or full fine-tuning for domain-specific applications, with experience using Bedrock for fine-tuning workflows Evaluation Metrics: Familiarity with BLEU, ROUGE, perplexity, and custom metrics for agent performance Benefits
Generous cost sharing for medical insurance for the employee and dependents 100% company paid dental insurance for employees and dependents 100% company paid long-term and short-term disability insurance 100% company paid vision insurance for employees and dependents 401k plan with generous match and 100% immediate vesting Competitive Pay Generous paid leave and holiday package Tuition and training reimbursement Life and AD&D Insurance About AnaVation
AnaVation is the leader in solving the most complex technical challenges for collection and processing in the U.S. Federal Intelligence Community. We are a US owned company headquartered in Chantilly, Virginia. We deliver groundbreaking research with advanced software and systems engineering that provides an information advantage to contribute to the mission and operational success of our customers. We offer complex challenges, a top-notch work environment, and a world-class, collaborative team. If you want to grow your career and make a difference while doing it, AnaVation is the perfect fit for you! AnaVation is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to sex, race, color, religion, national origin, disability, protected Veteran status, age, or any other characteristic protected by law.
#J-18808-Ljbffr