Machine Learning Engineer

• Design multi-agent architectures: define agent roles (planner, researcher, retriever, executor, reviewer), toolboxes, handoffs, memory strategy (short/long-term), and supervisor policies for safe collaboration.
• Build high-quality RAG: implement ingestion, chunking, embeddings, indexing, and retrieval with evaluation (precision/recall, groundedness, hallucination checks), guardrails, and citations.
• Productionize on AWS: leverage services like Bedrock (Agents/Knowledge Bases/Flows), Lambda, API Gateway, S3, DynamoDB, OpenSearch/Vector DB, Step Functions, and CloudWatch for tracing and alerts.
• MLOps/LLMOps: automate CI/CD (GitOps), containerization (Docker/Kubernetes), infra-as-code, secrets/IAM, blue green/rollbacks, and data/feature pipelines.
• Observability & evaluation: instrument telemetry (traces, token/cost, latency), build dashboards (Grafana/CloudWatch), add human-in-the-loop review, A/B testing, and continuous offline/online evals.
• Operate reliably at scale: implement caching, rate-limit management, queueing, idempotency, and backoff; proactively detect drift and degradation.
• Collaborate & communicate partner with infra/DevOps/data/architecture teams; document designs, SLIs/SLOs, runbooks; present status and insights to technical and non-technical stakeholders.

• Bachelor's degree in computer science, Data Science, Engineering, or related field-or equivalent experience.
• Proven experience building agentic systems (single or multi-agent) and RAG pipelines in production.
• Strong cloud background for AI/ML workloads; familiarity with Bedrock or equivalent LLM platforms.
• Solid CI/CD and containerization skills (Git, Docker, Kubernetes) and infra-as-code fundamentals.
• Knowledge of data governance and model accountability throughout the MLOps/LLMOps lifecycle.
• Excellent communication, collaboration, and problem-solving skills; ability to work independently and within cross-functional teams.
• Passion for Generative AI and the impact of agent-based solutions across industries.

Preferred / Good to Have

• Experience with AWS Bedrock Agents/Knowledge Bases/Flows, OpenSearch (or other vector databases), Step Functions, Lambda, API Gateway, DynamoDB, S3.
• Dataiku platform exposure-govern, approvals, artifacts, MLOps deployment flows; SageMaker for custom model hosting.
• Familiarity with agent frameworks (e.g., LangGraph, crewAI, Semantic Kernel, AutoGen) and evaluation frameworks (guardrails, groundedness, hallucination checks).
• Covered these Dataiku Certifications (nice to have): ML Practitioner, Advanced Designer, MLOps Practitioner.