Full Stack AI Engineer

Job description:

We are looking for a Full Stack AI Engineer to help build and scale ciATHENA, CustomerInsights.AI's agentic AI platform for life sciences.

This is a hands-on product engineering role for someone who can work across the stack - from modern web applications and APIs to LLM-powered workflows, agent orchestration, enterprise data integration, and production deployment.

You will work closely with product managers, AI engineers, data engineers, architects, and domain experts to convert complex commercial life sciences workflows into intuitive, production-grade AI applications.

We are looking for someone comfortable operating in a 0-to-1 product environment, where requirements evolve quickly and engineers are expected to take ownership from problem definition through deployment.

Key Responsibilities:

• Design and build production-grade AI applications using modern frontend, backend, and GenAI technologies.
• Develop intuitive user experiences for conversational AI, analytics, agent workflows, and decision-support applications.
• Build scalable backend APIs and services for AI-powered applications using Python-based frameworks such as FastAPI.
• Integrate LLMs and AI models from providers such as Anthropic, OpenAI, Azure OpenAI, and open-source models.
• Build and integrate RAG pipelines, knowledge retrieval, semantic search, tool calling, and multi-agent workflows.
• Develop capabilities that allow agents to interact securely with enterprise data, APIs, applications, and analytical workflows.
• Work with structured and unstructured data across Snowflake, Databricks, relational databases, object stores, and vector databases.
• Implement conversational and agentic workflows that can reason across data, documents, business rules, and domain-specific knowledge.
• Develop reusable UI components and product frameworks for multiple ciATHENA applications and use cases.
• Implement authentication, authorization, SSO, RBAC, audit logging, and enterprise security controls.
• Build AI observability, evaluation, tracing, monitoring, and feedback mechanisms.
• Optimize AI applications for performance, reliability, latency, and cost.
• Containerize and deploy services using Docker and cloud-native technologies.
• Participate in architecture decisions, code reviews, testing, CI/CD, and production support.
• Work closely with Forward-Deployed AI Engineers to rapidly configure and deploy customer-specific use cases.
• Translate product requirements and business workflows into working software with minimal handoffs.

Core Technology Stack:

• Frontend
  • React
  • Next.js
  • TypeScript / JavaScript
  • Modern component libraries
  • Responsive enterprise application design
  • Data visualization
• Backend
  • Python
  • FastAPI / Flask / Django
  • REST APIs
  • Async programming
  • Microservices architecture
• AI / GenAI
  • Claude / Anthropic APIs
  • OpenAI / Azure OpenAI
  • Prompt engineering
  • Tool/function calling
  • Retrieval-Augmented Generation
  • Agentic workflows
  • Multi-agent systems
  • Structured outputs
  • Embeddings and semantic search
• AI Frameworks
  • LangGraph / LangChain
  • LlamaIndex or equivalent frameworks
  • Model Context Protocol (MCP) familiarity is a plus
• Data
  • SQL
  • PostgreSQL / Azure SQL
  • Snowflake
  • Databricks
  • Vector databases
  • Object storage
  • Data APIs and semantic layers
• Cloud / DevOps
  • Azure preferred
  • Docker
  • Kubernetes / Azure Container Apps
  • GitHub Actions / CI/CD
  • Terraform exposure is a plus
  • Logging, monitoring, and observability

What We're Looking For:

• 4-6 years of software engineering experience with strong full-stack development capability.
• At least 1-2 years of hands-on experience building applications using LLMs or GenAI technologies.
• Strong Python development skills.
• Strong experience with React, Next.js, TypeScript, or equivalent modern frontend frameworks.
• Experience building APIs, backend services, and distributed applications.
• Hands-on experience integrating LLMs into production applications.
• Understanding of RAG, embeddings, vector search, prompt design, and agent architectures.
• Ability to work with enterprise data platforms and relational databases.
• Strong understanding of software engineering fundamentals, design patterns, testing, and maintainability.
• Experience building secure enterprise applications with authentication and authorization.
• Ability to independently take a feature from concept to production.
• Comfort working in a fast-moving startup/product environment with evolving requirements.
• Strong problem-solving ability and willingness to work across traditional frontend, backend, data, and AI boundaries.

Strongly Preferred:

• Experience building agentic AI products, not just chatbots.
• Experience with LangGraph or similar orchestration frameworks.
• Experience building enterprise SaaS or AI products from 0 to 1.
• Experience integrating AI applications with Snowflake or Databricks.
• Familiarity with semantic layers, metadata catalogs, knowledge graphs, or enterprise search.
• Experience with AI evaluation frameworks, tracing, observability, and hallucination mitigation.
• Experience implementing human-in-the-loop workflows.
• Experience with structured output validation and deterministic AI workflows.
• Experience with enterprise security, auditability, and governance requirements.
• Startup or product-company experience where engineers owned features end-to-end.

Bonus:

• Experience in life sciences, healthcare, commercial analytics, or pharmaceutical technology.
• Understanding of pharmaceutical datasets such as claims, sales, HCP/HCO, payer, patient, market access, or field-force data.
• Experience with enterprise AI platforms or commercial analytics applications.
• Contributions to open-source AI projects or demonstrated personal AI projects.

Profile We Are Looking For:

This is not a role focused on building another generic agent or chatbot.

ciATHENA is being built as a hyper-verticalized agentic AI platform for life sciences, where agents need to understand domain context, interact with governed enterprise data, execute analytical workflows, collaborate with other agents, and produce auditable business decisions.

You will help build capabilities spanning: User Experience -> Agents -> Knowledge -> Data -> Analytics -> Enterprise Systems.

We therefore value engineers who can think beyond an individual technology layer and understand how the complete product works.

Skills

Gen AI, Generative AI, JavaScript, LLM, Next.js, Python, React, TypeScript