Senior Gen AI Engineer

Fractal Analytics; Massachusetts; On-site; USD 120,000 - 150,000; Full time

Benefits offered by this job

Health benefits

401(k) plan

11 paid holidays

12 weeks parental leave

Flexible PTO

Job summary

Fractal Analytics is hiring an onsite Senior Gen AI Engineer in Cambridge, MA. The role focuses on building scalable, secure GenAI platforms and agentic AI applications on AWS, with hands-on work across orchestration, governance, and cloud-native microservices.

You will work with Amazon Bedrock to drive LLM inference and model integrations, developing reusable APIs, SDKs, accelerators, and reference architectures for enterprise RAG systems and multi-agent workflows.

Qualifications

• 8-10 years of software engineering experience.
• 3+ years in GenAI or AI solution development.
• Strong Python proficiency and AWS experience.
• Experience with LLMs, model orchestration, and prompt engineering.

Responsibilities

• Design, develop, and maintain scalable GenAI platforms on AWS.
• Architect multi-agent AI solutions and orchestration frameworks.
• Build enterprise-grade RAG solutions using embeddings and vector databases.
• Develop AI applications leveraging Bedrock for model orchestration and prompts.
• Create evaluation, benchmarking, governance, and security frameworks.
• Develop observability with telemetry, monitoring, tracing, and dashboards.
• Design cloud-native microservices and APIs using Python and CI/CD pipelines.

Skills

GenAI

Agentic AI

Python

AWS

Cloud architecture

Kubernetes

CI/CD

Observability

Security governance

Tools

AWS Bedrock

Terraform

Docker

OpenSearch

ECS/EKS

Job description

Fractal Analytics is hiring an onsite Senior Gen AI Engineer in Massachusetts (Cambridge, MA). This role focuses on building scalable, secure, production-grade GenAI and agentic AI platforms and applications on AWS, with hands-on work across orchestration, evaluation, governance, observability, and cloud-native microservices.

You will work with Amazon Bedrock to drive LLM inference and foundation model integrations, while developing reusable components such as APIs, SDKs, accelerators, and reference architectures. The platform you help create will support enterprise RAG systems, multi-agent workflows, and knowledge-driven AI using tools like embeddings, vector stores, and knowledge graphs.

What you'll do

• Design, develop, and maintain scalable, secure, highly available GenAI platforms and AI applications on AWS.
• Architect and implement Agentic AI solutions, including multi-agent systems, tool and function calling, and orchestration frameworks.
• Build enterprise-grade RAG solutions using embeddings, vector databases, semantic search, reranking, and retrieval pipelines.
• Develop AI applications leveraging Amazon Bedrock for model orchestration, prompt management, and foundation model integrations.
• 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 capabilities including telemetry, monitoring, tracing, logging, and operational dashboards.
• Design and develop cloud-native microservices and APIs using Python and modern software engineering practices.
• Automate infrastructure provisioning and deployment using Terraform and Infrastructure as Code (IaC), and maintain CI/CD pipelines.
• Collaborate with cross-functional teams across engineering, security, product, and business to drive AI platform adoption and best practices.
• Mentor junior engineers and contribute to architecture reviews and technical leadership initiatives.

Key skills and experience

• 8-10 years of software engineering experience, including 3+ years in GenAI or 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).
• Experience designing and implementing RAG architectures (embeddings, vector databases, retrieval pipelines, reranking, 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 Python proficiency for backend development, AI application development, and API implementation.
• Experience with AWS services including Bedrock, Lambda, ECS/EKS, API Gateway, S3, IAM, CloudWatch, DynamoDB, OpenSearch, and Step Functions.
• Experience with Terraform and Infrastructure as Code for cloud automation and platform deployment.
• Background building cloud-native applications using APIs, microservices, Docker, Kubernetes, and CI/CD pipelines.
• Understanding of AI observability including monitoring, tracing, and telemetry.
• Knowledge of relational, NoSQL, vector, and graph databases, plus security, governance, compliance, and responsible AI frameworks.

Preferred / good-to-have

• LangChain, LangGraph, Semantic Kernel.
• LlamaIndex.
• OpenAI Agents SDK or similar agent frameworks.
• Vector database options such as Amazon OpenSearch, Pinecone, Weaviate, Chroma, or FAISS.
• OpenTelemetry, Langfuse, Arize Phoenix, or MLflow.
• Grafana, Prometheus, and CloudWatch observability.
• Neo4j and knowledge graph technologies.
• MLOps / LLMOps experience, and exposure to fine-tuning, model evaluation, and AI benchmarking frameworks.

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 that allows flexibility to take time needed for sick time or vacation.

Pay

$120,000-$150,000 per year (reasonable estimate of the current range). A discretionary bonus may be available for the current performance period.