ML Engineer I

Role Description Senior AI Engineer (GenAI + Data Platform - AWS) Role Summary We are seeking a Senior AI Engineer to build and scale a production-grade GenAI and data platform on AWS, enabling LLM-powered capabilities through vector search, graph databases, and governed data pipelines. This role owns end-to-end delivery across the AI lifecycle from data ingestion and knowledge curation embeddings and retrieval systems backend services and APIs CI/CD and deployment. You will partner closely with product and engineering teams to operationalize AI capabilities in externally facing applications. This position also plays a key role in building and evolving our platform toward agentic systems, including implementing tooling, memory, state management, and guardrails, with all future enhancements and capabilities designed and delivered by our team. Key Responsibilities GenAI Enablement & Integration

• Enable LLM-powered use cases using patterns such as retrieval-augmented generation (RAG), embeddings pipelines, prompt orchestration, and evaluation strategies.
• Design and implement vector-based retrieval systems using Amazon OpenSearch (vector capabilities).
• Build and maintain graph-based knowledge systems using Amazon Neptune to support entity relationships, lineage, and explainability.
• Integrate supporting infrastructure: + Amazon ElastiCache (Redis) for low-latency caching and session state + DynamoDB for high-scale, low-latency data access patterns
• Implement and operate production-grade LLM workflows and agentic patterns using frameworks such as LangGraph, AutoGen, or CrewAI (or equivalent).
• Integrate LLM application frameworks such as LangChain and/or LlamaIndex, including tool calling, retrieval orchestration, and context management.
• Establish standards for tool integration and context-sharing patterns (e.g., Model Context Protocol (MCP)-style designs), preparing the platform for Agent Core adoption.
• Evaluate and compare LLMs and retrieval strategies across latency, cost, accuracy, and context limitations, selecting optimal approaches for production use cases. Data Pipelines & Knowledge Engineering
• Design, build, and operate scalable data pipelines using Databricks, including: + Data ingestion and transformation + Document processing (chunking, metadata tagging) + Embedding generation and indexing
• Build distributed data processing jobs leveraging Apache Spark (Databricks) for large-scale transformation and enrichment.
• Ensure high standards for data quality, including validation, completeness, consistency, and monitoring.
• Implement and enforce data governance practices: + Data classification and access controls + Retention policies + Auditability and lineage tracking Backend Services & APIs
• Build and maintain backend services that expose AI and data capabilities through secure, scalable APIs.
• Define service contracts, versioning strategies, and reliability patterns (e.g., retries, circuit breakers, idempotency).
• Enable reuse of platform capabilities across multiple applications and teams. Deployment, MLOps & Operational Excellence
• Own and evolve CI/CD pipelines for AI services and data workloads.
• Build production-grade AI systems using Docker-based containerization and Kubernetes orchestration.
• Implement safe deployment strategies (e.g., blue/green, canary releases, rollback mechanisms, feature flags).
• Ensure systems are secure, observable, and reliable, including: + Monitoring and ing (latency, errors, cost, data freshness) + Secrets management and least-privilege access controls + Performance and cost optimization LLM Observability, Evaluation & Quality
• Define and operationalize GenAI quality metrics, including: + Grounding/faithfulness + Retrieval relevance + Response consistency + Latency and cost per request
• Implement evaluation and observability workflows for LLM and RAG systems, including prompt/version tracking, offline testing, and continuous improvement loops. LLM Security, Safety & Compliance
• Implement security controls for LLM-powered systems, including defenses against: + Prompt injection + Data leakage and exfiltration + Unsafe tool execution + Retrieval/data poisoning risks
• Apply secure-by-design practices aligned to enterprise standards, including least privilege access, audit logging, and data governance controls, particularly within regulated environments. Agentic Systems Evolution (Future-Focused)
• Design foundational capabilities to support agent-based architectures, including: + Tool integration patterns + Memory and state management + Guardrails and policy enforcement
• Drive innovation in agentic systems; all related enhancements will be developed and delivered by this team.

Required Qualifications

• 5+ years of experience in software engineering, data engineering, or AI/ML engineering
• Strong proficiency in Python for AI/data workflows and automation
• Hands-on experience building solutions in AWS cloud environments
• Experience with: + Databricks (or similar) and Apache Spark for distributed data processing + OpenSearch / Elasticsearch (including vector search) + Graph databases (Neptune or similar) + DynamoDB and Redis/ElastiCache
• Experience building backend services and APIs (e.g., Java/Spring Boot, Node.js)
• Production experience with Docker and Kubernetes
• Experience with CI/CD pipelines and deployment automation
• Strong understanding of distributed systems, data architecture, and scalable design

Preferred Qualifications

• Experience with LLM/GenAI architectures (RAG, embeddings, prompt engineering)
• Familiarity with LangGraph, AutoGen, CrewAI, or similar agent orchestration frameworks
• Experience with LangChain or LlamaIndex
• Experience implementing LLM evaluation and observability frameworks
• Familiarity with AI security practices and threat models (prompt injection, guardrails)
• Experience working in regulated environments with strong data governance and compliance requirements What You ll Own / Impact
• End-to-end ownership of a modern AI platform powering external-facing digital experiences
• Establishment of best practices for GenAI integration, evaluation, and security
• Advancement of the organization toward agentic AI capabilities, with your team leading all related innovation and delivery Tech Stack (Representative)
• AWS: Neptune, OpenSearch, DynamoDB, ElastiCache (Redis), IAM, CloudWatch
• Data: Databricks, Apache Spark
• AI: LLM integrations, embeddings, vector search, RAG pipelines
• Agentic/LLM Tooling: LangChain, LlamaIndex, LangGraph, AutoGen, CrewAI
• Backend: APIs, microservices (e.g., Spring Boot, Node.js)
• DevOps: Docker, Kubernetes, CI/CD, Infrastructure as Code

Skills data science,artificial intelligence,ai system,kubernetes orchestration,aws,java,