Confirmed on the employer's own hiring board on Nov 19, 2026. First seen by Alion on Nov 19, 2026. Symphoni HR scores A on the Alion truth index.
The AI Engineering Lead joins the Enterprise AI function and reports to the AVP / VP of Enterprise AI. This permanent, hybrid role combines hands-on development of production-scale AI solutions and platform components with rapid prototyping of copilots and agentic workflows. You will ship real software that stakeholders actually use, from early prototype through to production.
Our client is a leading global computer software company with a large, international customer base. They are known for building enterprise technology at scale and for a culture that values innovation, ownership and practical impact.
Responsibilities
- Build AI applications, copilots and agentic workflows end-to-end, including UI, APIs, business logic and model integration.
- Use rapid development tools such as Cursor, Claude Code, Replit and Google AI Studio to turn loosely defined requirements into working prototypes and refine them based on feedback.
- Develop with agentic SDKs and frameworks such as OpenAI Agents SDK, Anthropic Claude, Google Gemini / ADK and LangChain / LangGraph, implementing RAG pipelines, tool calling, structured outputs and systematic evals.
- Integrate models and agents with enterprise data sources and APIs, handling authentication, rate limits and error paths.
- Partner with Forward Deployment Engineers and platform teams to productionize prototypes with monitoring, guardrails and cost controls.
- Apply enterprise design principles including responsible and secure AI, observability, LLMOps and token economics, aligned to Agentic AI technical architecture standards.
Requirements
- 8+ years of software engineering experience, with 2+ years building GenAI / LLM applications hands-on.
- Strong Python and/or TypeScript / JavaScript skills, including full-stack prototyping with React / Node and REST APIs.
- Hands-on experience with agentic frameworks and LLM patterns: prompt engineering, function calling and RAG with vector stores such as pgvector, Pinecone or FAISS.
- Testing and observability experience, including evals and tracing tools such as LangSmith or Langfuse.
- Engineering foundations in Git, Docker, CI/CD and at least one cloud platform (AWS, Azure or GCP).
- A portfolio of shipped AI work you can walk us through, with clear communication for technical and business audiences.
- Nice to have: voice or multimodal experience (ElevenLabs, HeyGen), MCP-based tool integration, or fine-tuning and open-source LLM experience.
- Bachelor's degree in Computer Science, Engineering or a related field, or equivalent practical experience.
Skills
Python, TypeScript / JavaScript, React, Node.js, REST APIs, RAG pipelines, LLM prompt engineering and function calling, Git, Docker, CI/CD, Cloud platform (AWS, Azure, or GCP), OpenAI Agents SDK, Anthropic Claude, Google Gemini / ADK, LangChain / LangGraph, pgvector / Pinecone / FAISS, LangSmith / Langfuse, Cursor / Claude Code / Replit / Google AI Studio, ElevenLabs / HeyGen, MCP-based tool integration, Fine-tuning and open-source LLM experience

