Senior Gen AI Engineer

Fractal Analytics is seeking a Senior GenAI Engineer to help design, build, and maintain scalable, secure, production-grade GenAI and agentic AI platforms and applications. Based in Massachusetts (onsite) in Cambridge, this role focuses on cloud-native delivery on AWS, with an emphasis on Amazon Bedrock, orchestration, evaluation, governance, and observability.

You will work across the stack of modern LLM systems, from RAG architecture and knowledge retrieval to CI/CD and infrastructure automation, using Python and Infrastructure as Code to support reliable platform growth.

Responsibilities

• Design, develop, and maintain scalable, secure, highly available GenAI platforms and AI-powered applications on AWS.
• Architect and implement Agentic AI solutions, including multi-agent systems, tool integrations, function calling, and workflow orchestration frameworks.
• Design and implement enterprise-grade RAG solutions using embeddings, vector databases, semantic search, reranking, and knowledge retrieval techniques.
• Build AI applications leveraging Amazon Bedrock for LLM inference, model orchestration, prompt management, and foundation model integrations.
• Create reusable AI platform components such as SDKs, APIs, accelerators, and reference architectures.
• Develop knowledge-driven AI systems using vector stores, graph databases, and knowledge graph technologies.
• Create evaluation and benchmarking frameworks to measure AI quality, accuracy, latency, safety, and performance.
• Implement AI governance, security controls, responsible AI practices, guardrails, and compliance mechanisms.
• Develop observability including telemetry, monitoring, tracing, logging, and operational dashboards.
• Design and develop cloud-native microservices and APIs using Python and modern software engineering practices.
• Automate cloud infrastructure provisioning and deployment using Terraform and Infrastructure as Code principles.
• Build and maintain CI/CD pipelines for AI and cloud workloads.
• Collaborate with engineering, security, product, and business teams to drive AI platform adoption and best practices.
• Mentor junior engineers and contribute to architecture reviews and technical leadership initiatives.

Requirements

• 8–10 years of software engineering experience, including 3+ years in GenAI/AI solution development.
• Strong hands-on experience building production-grade Generative AI solutions.
• Expertise in Agentic AI, AI Agents, multi-agent architectures, tool calling, function calling, orchestration, and MCP (Model Context Protocol).
• Strong experience designing and implementing RAG architectures, including embeddings, vector databases, retrieval pipelines, reranking, and semantic search.
• Hands-on experience with Amazon Bedrock, foundation model integration, inference optimization, prompt engineering, and model orchestration.
• Deep understanding of LLMs, prompt engineering, evaluation, model selection, and deployment patterns.
• Strong proficiency in Python for backend and AI application development, including API implementation.
• Strong experience with AWS services including Bedrock, Lambda, ECS/EKS, API Gateway, S3, IAM, CloudWatch, DynamoDB, OpenSearch, Step Functions, and related services.
• Experience with Terraform and Infrastructure as Code for cloud automation and platform deployment.
• Experience building cloud-native applications using APIs, Microservices, Docker, Kubernetes, and CI/CD.
• Understanding of AI observability, monitoring, tracing, and telemetry.
• Knowledge of relational, NoSQL, vector, and graph databases.
• Experience with security, governance, compliance, and responsible AI frameworks.

Technologies

• GenAI, Agentic AI, RAG, Amazon Bedrock, AWS Cloud, Python, Terraform
• LangChain, LangGraph, LlamaIndex, OpenSearch, Vector Databases, MCP (Model Context Protocol)
• AI Observability, LLMOps, Microservices, Knowledge Graphs, Docker, Kubernetes, CI/CD
• Embeddings, Semantic search, Reranking, Graph databases, Knowledge retrieval techniques
• Telemetry, Monitoring, Tracing, Logging, API Gateway, S3, IAM, CloudWatch, DynamoDB, Step Functions, Lambda, ECS, EKS
• Function calling, Prompt management, Foundation model integrations, Prompt engineering, Model orchestration

Benefits

• Health, dental, vision, life insurance, and disability plans (eligible in accordance with plan documents).
• Eligible for benefits on the first day of employment.
• Participation in the Company 401(k) Plan after 30 days of employment (in accordance with plan terms).
• 11 paid holidays.
• 12 weeks of Parental Leave.
• “Free time” PTO policy for flexibility to take time needed for either sick time or vacation.

Preferred / Good-to-Have Skills

• LangChain, LangGraph, Semantic Kernel.
• LlamaIndex.
• OpenAI Agents SDK or similar agent frameworks.
• Amazon OpenSearch, Pinecone, Weaviate, Chroma, FAISS, or similar vector database technologies.
• OpenTelemetry, Langfuse, Arize Phoenix, MLflow.
• Grafana, Prometheus, CloudWatch Observability.
• Neo4j and knowledge graph technologies.
• Experience with distributed systems and scalable platform engineering.
• Experience with MLOps, LLMOps, and AI deployment pipelines.
• Exposure to fine-tuning, model evaluation, and AI benchmarking frameworks.

Pay

• Estimated base range: $120,000-$150,000 per year.
• Discretionary bonus eligibility may apply for the current performance period.

Location: Cambridge, MA area (onsite).

Minimum experience: 3 years in GenAI/AI solution development.