AI Developer

WISETEK PROVIDERS INC•Washington , DC

3d•$75,000 - $85,000•Hybrid

About The Position

The role seeks an AI-native, full-stack software developer with an AI-first engineering mindset. The developer should select appropriately between deterministic code, large language models, and agents, and design for probabilistic outputs using robust fallbacks while balancing cost, latency, and reliability. Core work includes integrating LLMs into production, prompt engineering, structured outputs, retrieval-augmented generation (RAG), context management, and evaluating quality and hallucinations. The position also involves rapidly prototyping, iterating on, and deploying AI capabilities; developing autonomous or semi-autonomous agents; building full-stack applications; and working with cloud-native systems and data pipelines. The role emphasizes reliability, security, responsible AI, collaboration, clear communication, and production-quality craftsmanship. The position is listed as a six-month engagement with a possible extension. It is based in Washington, DC, and seeks local candidates. The work arrangement is hybrid, requiring onsite work four days per week from day one, with a full transition to 100% onsite anticipated soon.

Requirements

3 to 5 years of experience, excluding college period.
Expertise integrating LLMs into production, prompt engineering, structured outputs, RAG pipelines, context management, and quality and hallucination evaluation.
Proficiency with modern AI development platforms, APIs, and tooling for rapid prototyping, iteration, and deployment.
Experience building autonomous or semi-autonomous agents with goals, constraints, orchestration patterns, tool-calling, state and memory handling, guardrails, and behavioral observability.
Full-stack capabilities, including backend API design (REST or GraphQL), secure services, data modeling, asynchronous workflows, and external integrations.
Frontend capabilities with modern frameworks such as React, AI-native UX, state management, and human-AI interaction patterns.
Cloud-native experience in containerized or microservice environments, including CI/CD for AI components, secure secrets handling, cost-aware designs, and performance optimization.
Experience handling structured and unstructured data and building pipelines involving preprocessing, embeddings, ranking, and AI artifact versioning.
Ability to address reliability, security, and responsible AI, including sensitive-data protection, risk mitigation, auditability, and graceful degradation.
Excellent collaboration and communication skills, including explaining AI behavior, working cross-functionally, documenting, and critically reviewing outputs.
High learning agility and craftsmanship, with the ability to stay current with evolving AI tools and deliver production-quality systems.

Responsibilities

Choose between deterministic code, LLMs, and agents to address engineering needs, designing for probabilistic outputs with robust fallback strategies.
Integrate LLMs into production and implement prompt engineering, structured outputs, RAG pipelines, context management, and quality and hallucination evaluation.
Rapidly prototype, iterate on, and deploy functional AI capabilities into real-world systems using modern AI platforms, APIs, and tooling.
Build autonomous or semi-autonomous agents with defined goals and constraints, orchestration, tool-calling, state and memory handling, guardrails, and behavioral observability.
Develop backend services, including REST or GraphQL APIs, secure services, data models, asynchronous workflows, and external integrations.
Develop frontend experiences using modern frameworks and AI-native UX patterns, including streaming responses, explainability, state management, and human-AI interaction patterns.
Work in containerized, microservice, cloud-native environments and support CI/CD for AI components, secure secrets handling, cost-aware design, and performance optimization.
Build data and knowledge pipelines for structured and unstructured data, including preprocessing, embeddings, ranking, and AI artifact versioning.
Safeguard sensitive data, mitigate leakage, bias, and safety risks, ensure auditability, and support graceful degradation.
Collaborate across functions, document work, explain AI behavior clearly, and critically review outputs.
Stay current with evolving AI tools and deliver production-quality systems.