We are hiring a Forward-Deployed AI Specialist to design, build, and deploy production-grade AI solutions.
This is a high-impact, hands-on engineering role focused on rapid execution - owning the full lifecycle from problem definition to deployment. You will work directly with business stakeholders to deliver measurable ROI through AI-driven automation.
Core Responsibilities
AI Engineering & Solution Development
- Build and deploy AI-powered automation systems:
- Agentic workflows
- LLM-based assistants
- Document processing pipelines
- Design and implement RAG pipelines, context management, and memory systems
- Develop custom tools, plugins, and MCP integrations for extending LLM capabilities
- Apply prompt engineering, evaluation frameworks, and guardrails for production reliability
- Work with modern AI development ecosystems:
- LLM platforms (OpenAI, Anthropic, Gemini, etc.)
- AI coding tools (Cursor, Windsurf, etc.)
Required Programming Skills:
- Strong coding skills and OOP experience in:
- Python (preferred)
- JavaScript / TypeScript
- Experience building production-grade backend systems
AI / LLM Expertise:
- Hands-on experience with:
- Prompt engineering
- RAG (Retrieval-Augmented Generation)
- LLM orchestration frameworks
- Experience designing:
- AI agents
- Multi-step workflows
- Context-aware systems
- Experience with:
- API integrations and microservices
- Webhooks, queues, async workflows
- Familiarity with:
- Vector databases
- Embeddings and semantic search
Backend Engineering & APIs
- Design and build scalable backend using:
- Node.JS (Express / Nest JS)
- Python (FastAPI / Flask / Django)
- Develop and expose REST / GraphQL APIs for AI Services.
- Implement async processing, job queues, and event-driven workflows.
