Raas Infotek LLC
Job Title: AI/ML Engineer
Location: Charlotte, NC (Hybrid)
Employment Type: W2 Only (No C2C/1099)
Duration: 12 Months
About the Role
We are seeking a highly skilled
AI/ML Engineer
to design, build, and optimize advanced AI systems leveraging
Retrieval-Augmented Generation (RAG)
,
multi-modal models
, and
agentic architectures . This role combines deep technical expertise with strategic vision to deliver production‑grade AI solutions at scale. You will work on cutting‑edge technologies, including large‑scale knowledge bases, vector search, and autonomous AI agents, driving innovation end‑to‑end. Key Responsibilities
Architect & Optimize RAG Pipelines:
Build complex RAG systems for multi‑domain knowledge bases, TB‑scale datasets, and advanced chunking/indexing strategies. Lead Multi‑Modal AI Experiments:
Develop solutions across text, image, and diagram‑based use cases. Knowledge Graph Solutions:
Design and maintain graph‑driven retrieval and reasoning systems. Agentic AI Systems:
Create autonomous, task‑oriented agents with tool augmentation beyond conversational AI. Research & Evaluation:
Stay ahead of emerging AI techniques; define evaluation frameworks for performance, safety, and reliability. Observability & Monitoring:
Implement telemetry, tracing, and error detection for LLM‑driven workflows. Hands‑On Development:
Work with OpenAI APIs and similar platforms; apply prompt engineering and LLM design patterns. Software Engineering:
Develop robust Python‑based solutions for data processing, orchestration, and integration. Vector Database Optimization:
Leverage vector stores for semantic search and scalable indexing. Qualifications
Experience:
8 years in software engineering or applied ML. Proven track record in
production‑scale RAG systems . Strong knowledge of embeddings, vector similarity search, and retrieval optimization. Hands‑on experience with
multi‑modal models
(VLMs, OCR, vision‑language reasoning). Familiarity with
knowledge graphs
(Neo4j, RDF, graph embeddings). Prior work on
agentic/LLM‑driven systems
(tool use, planning, function calling). Advanced
Python engineering skills
and modern development practices. Experience with
AI observability frameworks , experiment tracking, and evaluation tooling. Proficiency with
OpenAI APIs
or similar LLM platforms. Ability to translate cutting‑edge research into practical solutions. Nice to Have
Experience with
distributed systems
and high‑volume data processing. Background in
ML Ops , GPU orchestration, or model deployment pipelines. Expertise in
search systems , IR, or NLP.
#J-18808-Ljbffr
We are seeking a highly skilled
AI/ML Engineer
to design, build, and optimize advanced AI systems leveraging
Retrieval-Augmented Generation (RAG)
,
multi-modal models
, and
agentic architectures . This role combines deep technical expertise with strategic vision to deliver production‑grade AI solutions at scale. You will work on cutting‑edge technologies, including large‑scale knowledge bases, vector search, and autonomous AI agents, driving innovation end‑to‑end. Key Responsibilities
Architect & Optimize RAG Pipelines:
Build complex RAG systems for multi‑domain knowledge bases, TB‑scale datasets, and advanced chunking/indexing strategies. Lead Multi‑Modal AI Experiments:
Develop solutions across text, image, and diagram‑based use cases. Knowledge Graph Solutions:
Design and maintain graph‑driven retrieval and reasoning systems. Agentic AI Systems:
Create autonomous, task‑oriented agents with tool augmentation beyond conversational AI. Research & Evaluation:
Stay ahead of emerging AI techniques; define evaluation frameworks for performance, safety, and reliability. Observability & Monitoring:
Implement telemetry, tracing, and error detection for LLM‑driven workflows. Hands‑On Development:
Work with OpenAI APIs and similar platforms; apply prompt engineering and LLM design patterns. Software Engineering:
Develop robust Python‑based solutions for data processing, orchestration, and integration. Vector Database Optimization:
Leverage vector stores for semantic search and scalable indexing. Qualifications
Experience:
8 years in software engineering or applied ML. Proven track record in
production‑scale RAG systems . Strong knowledge of embeddings, vector similarity search, and retrieval optimization. Hands‑on experience with
multi‑modal models
(VLMs, OCR, vision‑language reasoning). Familiarity with
knowledge graphs
(Neo4j, RDF, graph embeddings). Prior work on
agentic/LLM‑driven systems
(tool use, planning, function calling). Advanced
Python engineering skills
and modern development practices. Experience with
AI observability frameworks , experiment tracking, and evaluation tooling. Proficiency with
OpenAI APIs
or similar LLM platforms. Ability to translate cutting‑edge research into practical solutions. Nice to Have
Experience with
distributed systems
and high‑volume data processing. Background in
ML Ops , GPU orchestration, or model deployment pipelines. Expertise in
search systems , IR, or NLP.
#J-18808-Ljbffr