AI Native Full stack Developer

Title:  AI Native Full Stack Developer

Project Duration: 6 months

Interview mode: Virtual

Location: Washington, DC 20433 – Hybrid (Only local Candidates)

Note: This is not a Java Full Stack role. 

• AI‑Native Software Developer Profile (GenAI & Agentic AI, Full‑Stack) We seek developers with an AI‑first engineering mindset, able to choose between deterministic code, LLMs, and agents, and to design for probabilistic outputs with robust fallback strategies while balancing cost, latency, and reliability.
• Core GenAI & LLM expertise includes integrating LLMs into production, prompt engineering, structured outputs, RAG pipelines, effective context management, and quality/hallucination evaluation. 
• Rapid solution development skills: proficiency with modern AI development platforms, APIs, and tooling to quickly prototype, iterate, and deploy functional AI capabilities into real‑world systems. 
• Agentic AI experience: building autonomosemi‑autonomous agents with clear goals, constraints, orchestration patterns, tool‑calling, state/memory handling, guardrails, and behavioral observability. 
• Full‑stack capabilities: Backend — API design (REST/GraphQL), secure services, data modelling, async workflows, external integrations. Frontend — modern frameworks (e.g., React), AI‑native UX (streaming responses, explainability), state management, human‑AI interaction patterns.
• Cloud‑native experience in containerized/microservice environments, CI/CD for AI components, secure secrets handling, cost‑aware designs, and performance optimization. 
• Data & knowledge engineering: handling structured/unstructured data, building pipelines, preprocessing, embeddings, ranking, and versioning AI artifacts. 
• Focus on reliability, security, and responsible AI: safeguard sensitive data, mitigate leakage/bias/safety risks, ensure auditability, and support graceful degradation. 
• Excellent collaboration and communication: clear explanation of AI behaviour, cross‑functional teamwork, documentation, and critical output review. 
• High learning agility and craftsmanship: staying current with evolving AI tools, delivering production‑quality systems.