Guidehouse
Software Developer (Backend – Integration)
Guidehouse, Huntsville, Alabama, United States, 35824
Software Developer (Backend – Integration)
Guidehouse is seeking a Software Developer to join our Technology / AI and Data team, supporting mission‑critical initiatives for Defense and Security clients. In this role, you will lead the design and implementation of secure, scalable ingestion and data processing workflows that power advanced AI‑driven platforms. Job Family:
Data Science & Analysis Travel Required:
Up to 10% Clearance Required:
Active Top Secret (TS) What You Will Do
Lead backend integration engineering for the FBI adjudication AI platform, architecting ingestion, preprocessing, normalization, and transformation workflows. Design ingestion frameworks for SF‑86 forms, investigative attachments, summaries, financial/criminal records, and continuous vetting alerts using OCR and VLM/LLM‑based document understanding. Ensure workflows comply with FedRAMP High, RMF, CJIS, and FBI ATO requirements, including logging, auditability, encryption, and secure processing of PII. Collaborate with AI/ML engineers, backend API developers, cloud engineers, and security engineers to optimize ingestion outputs for RAG workflows, SEAD‑4 scoring, anomaly detection, and adjudicator review. Build scalable ingestion and ETL pipelines capable of processing hundreds of pages per case with Textract, Tesseract, LayoutLM, Qwen‑VL, Donut, or LLaVA. Develop fault‑tolerant ingestion systems with checkpointing, idempotency, retry frameworks, and structured error reporting. Create secure, compliant integrations with FBI systems, case repositories, identity/HR systems, and continuous vetting alert sources using APIs, ETL endpoints, SFTP, and message queues. Develop backend microservices that assemble case packages, correlate evidence across sources, and produce structured adjudication‑ready datasets. Integrate ingestion outputs with vector databases, embedding pipelines, and LLM inference services, ensuring data is enriched and optimized for reasoning workflows. Prepare documents and extracted content for embeddings, retrieval indexing, semantic search, and long‑context reasoning, implementing chunking, segmentation, labeling, and evidence‑tagging strategies. Apply PII‑safe processing techniques, automated redaction, VLM‑aided sensitive field detection, and compliance‑driven filtering. Optimize pipelines for parallelization, concurrency, batching, memory efficiency, and large‑scale document processing throughput. Develop monitoring dashboards capturing ingestion throughput, OCR accuracy metrics, error frequencies, latency patterns, and retry trends. Implement resilience features including dead‑letter queues, backoff retry mechanisms, fault isolation, and disaster‑recovery patterns. Participate in sprint ceremonies, architecture reviews, backlog refinement, and cross‑functional coordination with mission stakeholders. Mentor mid‑level engineers in ETL design, multimodal OCR techniques, distributed system patterns, and secure ingestion best practices. What You Will Need
Active and maintained Top Secret Federal or DoD security clearance. University degree and minimum 4–6 years of relevant experience (experience may substitute for formal education). 5+ years of backend/integration engineering experience, including 3+ years in large‑scale ETL or ingestion workflows. Deep experience with Python, Java, or Scala and ingestion frameworks such as Airflow, Step Functions, Dagster, or Glue. Experience with large‑scale document ingestion, OCR/VLM document understanding, unstructured data parsing. Experience developing secure data processing/normalization workflows. Experience with distributed processing frameworks. What Would Be Nice to Have
Experience integrating FBI, DCSA, or NBIB systems or adjudication‑related data sources. Experience designing ingestion workflows for RAG, embeddings, vector databases, or long‑context LLM pipelines. Experience training or applying VLMs such as LayoutLM, Donut, Qwen‑VL, or LLaVA for OCR enhancement. Experience with knowledge graphs, entity resolution, evidence‑linking workflow development. Familiarity with SEAD‑4, continuous vetting, or investigative case analysis processes. Knowledge of specific AWS ingestion tools (Glue, Batch, S3 eventing). What We Offer
Guidehouse offers a comprehensive total rewards package including competitive compensation and a flexible benefits package that reflects our commitment to a diverse and supportive workplace. Benefits Include
Medical, Rx, Dental & Vision Insurance Personal and Family Sick Time & Company Paid Holidays Discretionary variable incentive bonus opportunity Parental Leave and Adoption Assistance 401(k) Retirement Plan Basic Life & Supplemental Life Health Savings Account, Dental/Vision & Dependent Care FSA Short‑Term & Long‑Term Disability Student Loan PayDown Tuition Reimbursement, Personal Development & Learning Opportunities Skill Development & Certifications Employee Referral Program Corporate Sponsored Events & Community Outreach Emergency Back‑Up Childcare Program Mobility Stipend About Guidehouse
Guidehouse is an Equal Opportunity Employer–Protected Veterans, Individuals with Disabilities or any other basis protected by law, ordinance, or regulation. Guidehouse will consider qualified applicants with criminal histories in a manner consistent with applicable law or ordinance, including the Fair Chance Ordinance of Los Angeles and San Francisco. If you require an accommodation, please contact Guidehouse Recruiting at 1‑571‑633‑1711 or via email at RecruitingAccommodation@guidehouse.com. All information you provide will be kept confidential and used only to the extent required to provide necessary accommodation. All recruitment communications will be sent from Guidehouse email domains. Guidehouse will never charge a fee or require a money transfer at any stage of the recruitment process.
#J-18808-Ljbffr
Guidehouse is seeking a Software Developer to join our Technology / AI and Data team, supporting mission‑critical initiatives for Defense and Security clients. In this role, you will lead the design and implementation of secure, scalable ingestion and data processing workflows that power advanced AI‑driven platforms. Job Family:
Data Science & Analysis Travel Required:
Up to 10% Clearance Required:
Active Top Secret (TS) What You Will Do
Lead backend integration engineering for the FBI adjudication AI platform, architecting ingestion, preprocessing, normalization, and transformation workflows. Design ingestion frameworks for SF‑86 forms, investigative attachments, summaries, financial/criminal records, and continuous vetting alerts using OCR and VLM/LLM‑based document understanding. Ensure workflows comply with FedRAMP High, RMF, CJIS, and FBI ATO requirements, including logging, auditability, encryption, and secure processing of PII. Collaborate with AI/ML engineers, backend API developers, cloud engineers, and security engineers to optimize ingestion outputs for RAG workflows, SEAD‑4 scoring, anomaly detection, and adjudicator review. Build scalable ingestion and ETL pipelines capable of processing hundreds of pages per case with Textract, Tesseract, LayoutLM, Qwen‑VL, Donut, or LLaVA. Develop fault‑tolerant ingestion systems with checkpointing, idempotency, retry frameworks, and structured error reporting. Create secure, compliant integrations with FBI systems, case repositories, identity/HR systems, and continuous vetting alert sources using APIs, ETL endpoints, SFTP, and message queues. Develop backend microservices that assemble case packages, correlate evidence across sources, and produce structured adjudication‑ready datasets. Integrate ingestion outputs with vector databases, embedding pipelines, and LLM inference services, ensuring data is enriched and optimized for reasoning workflows. Prepare documents and extracted content for embeddings, retrieval indexing, semantic search, and long‑context reasoning, implementing chunking, segmentation, labeling, and evidence‑tagging strategies. Apply PII‑safe processing techniques, automated redaction, VLM‑aided sensitive field detection, and compliance‑driven filtering. Optimize pipelines for parallelization, concurrency, batching, memory efficiency, and large‑scale document processing throughput. Develop monitoring dashboards capturing ingestion throughput, OCR accuracy metrics, error frequencies, latency patterns, and retry trends. Implement resilience features including dead‑letter queues, backoff retry mechanisms, fault isolation, and disaster‑recovery patterns. Participate in sprint ceremonies, architecture reviews, backlog refinement, and cross‑functional coordination with mission stakeholders. Mentor mid‑level engineers in ETL design, multimodal OCR techniques, distributed system patterns, and secure ingestion best practices. What You Will Need
Active and maintained Top Secret Federal or DoD security clearance. University degree and minimum 4–6 years of relevant experience (experience may substitute for formal education). 5+ years of backend/integration engineering experience, including 3+ years in large‑scale ETL or ingestion workflows. Deep experience with Python, Java, or Scala and ingestion frameworks such as Airflow, Step Functions, Dagster, or Glue. Experience with large‑scale document ingestion, OCR/VLM document understanding, unstructured data parsing. Experience developing secure data processing/normalization workflows. Experience with distributed processing frameworks. What Would Be Nice to Have
Experience integrating FBI, DCSA, or NBIB systems or adjudication‑related data sources. Experience designing ingestion workflows for RAG, embeddings, vector databases, or long‑context LLM pipelines. Experience training or applying VLMs such as LayoutLM, Donut, Qwen‑VL, or LLaVA for OCR enhancement. Experience with knowledge graphs, entity resolution, evidence‑linking workflow development. Familiarity with SEAD‑4, continuous vetting, or investigative case analysis processes. Knowledge of specific AWS ingestion tools (Glue, Batch, S3 eventing). What We Offer
Guidehouse offers a comprehensive total rewards package including competitive compensation and a flexible benefits package that reflects our commitment to a diverse and supportive workplace. Benefits Include
Medical, Rx, Dental & Vision Insurance Personal and Family Sick Time & Company Paid Holidays Discretionary variable incentive bonus opportunity Parental Leave and Adoption Assistance 401(k) Retirement Plan Basic Life & Supplemental Life Health Savings Account, Dental/Vision & Dependent Care FSA Short‑Term & Long‑Term Disability Student Loan PayDown Tuition Reimbursement, Personal Development & Learning Opportunities Skill Development & Certifications Employee Referral Program Corporate Sponsored Events & Community Outreach Emergency Back‑Up Childcare Program Mobility Stipend About Guidehouse
Guidehouse is an Equal Opportunity Employer–Protected Veterans, Individuals with Disabilities or any other basis protected by law, ordinance, or regulation. Guidehouse will consider qualified applicants with criminal histories in a manner consistent with applicable law or ordinance, including the Fair Chance Ordinance of Los Angeles and San Francisco. If you require an accommodation, please contact Guidehouse Recruiting at 1‑571‑633‑1711 or via email at RecruitingAccommodation@guidehouse.com. All information you provide will be kept confidential and used only to the extent required to provide necessary accommodation. All recruitment communications will be sent from Guidehouse email domains. Guidehouse will never charge a fee or require a money transfer at any stage of the recruitment process.
#J-18808-Ljbffr