Senior Gen AI Engineer

We're seeking a hands-on Architect/Lead to design, build, and scale GenAI systems on Python and AWS. You'll own end-to-end architecture (LLMs, agents, RAG, evals), production readiness (security, cost, reliability), and developer experience-leveraging AWS (Sage Maker/Bedrock) and Model Context Protocol (MCP) for safe, modular tool access.

• Architect GenAI systems (text/image/code) with LLMs and agentic workflows (single-/multi-agent, tool calling, structured outputs/JSON schemas).
• Adopt MCP to standardize tool integrations: design/implement custom MCP servers (files, search, knowledge bases, business APIs) and client orchestration.
• Build RAG pipelines (chunking, embeddings, hybrid search, citations, reranking) with Pinecone/FAISS/Chroma/Open Search; implement knowledge refresh and governance.
• Engineer Python-based pipelines for ingestion, fine-tuning/parameter-efficient tuning (LoRA/QLoRA), evaluation, and deployment (FastAPI microservices).
• Design AWS architectures using Bedrock (models, Knowledge Bases, Agents), Sage Maker (training/inference, Feature Store), Lambda, ECS/EKS, API Gateway, S3, Dynamo
  
  DB, Step Functions, Private Link/VPC endpoints, KMS.
• Observability & evals: tracing (Open Telemetry/Lang Smith), offline/online evals (RAGAS/G-Eval), guardrails/toxicity/PII redaction, prompt/version management, A/B tests, canary rollouts.
• Performance & cost: prompt compression/caching, batch/streaming, GPU/Inferentia sizing, autoscaling, token and latency budgets.
• Security & governance: IAM least-privilege, KMS encryption, data residency, model/data lineage, approval workflows, policy-as-code; align with SOC2/ISO/HIPAA/PCI as applicable.
• Platform enablement: build reusable SDKs/templates, CI/CD for GenAI (infra as code, tests, eval gates), golden paths for product teams.
• Leadership: mentor AI engineers/data scientists; drive POCs to production; translate business requirements into measurable GenAI use cases and KPIs.

• Python:
  FastAPI, async I/O, testing;
  Lang Chain/Llama Index and/or Lang Graph for agent orchestration;
  PyTorch;
  Hugging Face Transformers.
• MCP: designing custom MCP servers/skills, permissioning and sandboxing tools, wiring MCP clients into apps/agents.
• LLMs: GPT/Claude/Gemini/Llama; prompt engineering, tool use/function calling, structured output, safety patterns.
• AWS AI/ML:
  Bedrock (models, Knowledge Bases, Agents for Bedrock), Sage Maker (training/hosting), Lambda, ECS/EKS, S3, API Gateway, Dynamo
  
  DB, Cloud Watch, Step Functions.
• Containers & CI/CD:
  Docker, ECS/EKS, IaC (CDK/Terraform), Git Hub Actions/Code Pipeline; blue/green and canary.
• MLOps/AIOps: model/package versioning, feature/embedding stores, eval harnesses, tracing, alerting, rollout/rollback strategies.
• Security/compliance: IAM, VPC, KMS, Secrets Manager, data masking/PII redaction, audit logging.

• PEFT/LoRA/QLoRA, distillation, retrieval-adapted adapters; vector compression (PQ/HNSW tuning).
• Gateway & caching: LLM gateways, response/prompt caches (Redis, Bedrock inference cache).
• Guardrails: policy engines (Rebuff/Guardrails.ai-style), content moderation, safety scoring.
• Front-ends:
  Streamlit/Gradio/Next.js;
  Web Socket streaming; enterprise SSO (Cognito/Okta).
• Data stack:
  Glue/Athena/Lake Formation;
  Kafka/MSK;
  Delta/Iceberg/Hudi.

• Capgemini supports all aspects of your well-being throughout the changing stages of your life and career. For eligible employees, we offer:
• Healthcare including dental, vision, mental health, and well-being programs
• Financial well-being programs such as 401(k) and Employee Share Ownership Plan
• Paid time off and paid holidays
• Paid parental leave
• Family building benefits like adoption assistance, surrogacy, and cryopreservation
• Social well-being benefits like subsidized back-up child/elder care and tutoring
• Mentoring, coaching and learning programs
• Employee Resource Groups
• Disaster Relief

Capgemini is an Equal Opportunity Employer encouraging diversity in the workplace. All qualified applicants will receive consideration for employment without regard to race, national origin, gender identity/expression, age, religion, disability, sexual orientation, genetics, veteran status, marital status or any other characteristic protected by law.

This is a general description of the Duties, Responsibilities and Qualifications required for this position. Physical, mental, sensory or environmental demands may be referenced in an attempt to communicate the manner in which this position traditionally is performed. Whenever necessary to provide individuals with disabilities an equal employment opportunity, Capgemini will consider reasonable accommodations that might involve varying job requirements and/or changing the way this job is performed, provided that such accommodations do not pose an undue hardship.

Capgemini is committed to providing reasonable accommodations during our recruitment process. If you need assistance or accommodation, please get in touch with your recruiting…