AI Senior Software Engineer

Overview

MUST BE A UNITED STATES CITIZEN

TOP SECRET
CLEARANCE REQUIRED

100% ONSITE - WASHINGTON, DC

NO THIRD PARTY VENDORS

SALARY IS DEPENDENT UPON THE CANDIDATE’S SKILLS, EXPERIENCE, EDUCATION AND CERTIFICATIONS Soft Tech offers competitive BENEFITS in the areas of: MEDICAL, DENTAL, VISION, 401K, Short Term Disability, Long Term Disability, Life Insurance, PTO, AND PAID HOLIDAYS

Soft Tech Consulting is seeking an AI Senior Software Engineer with strong technical acumen, creativity, and problem‑solving ability to design, implement, and optimize AI‑powered solutions built on modern agentic frameworks. In this role, you will develop intelligent workflows using foundation models (e.g., Claude Sonnet, Claude Opus, etc.), configure multi‑agent systems, integrate AI with enterprise applications and data systems, and iteratively tune and evaluate agent behavior to deliver reliable, real‑world outcomes.

The selected candidate will collaborate closely with a community of generative AI specialists, software engineers, data scientists, solution architects, cybersecurity experts, and product owners to deliver innovative, production‑ready AI systems that transform our clients’ ecosystems and reinvent the way they operate.

• Design, build, and optimize agentic AI systems using orchestration frameworks like Lang Graph, CrewAI, Google ADK, or AWS Bedrock Agent Core, etc.
• Implement multi‑step, tool‑enabled AI agentic workflows that combine LLM reasoning, RAG, retrieval systems, external APIs, and custom enterprise tools.
• Use leading foundation models (Claude Sonnet, Claude Opus, , etc.) on Amazon Bedrock to build capabilities including structured generation, extraction, summarization, planning, and decision support.
• Iteratively tune and refine AI workflows through prompt engineering, instruction design, agent configuration, and tool‑use optimization.
• Conduct structured testing and evaluation of AI behavior, including regression tests, scenario‑based evaluations, synthetic test creation, and model‑to‑model comparisons.
• Diagnose issues such as hallucinations, retrieval mismatches, tool‑use errors, or unexpected agent behavior, and implement corrective strategies including guardrails and workflow adjustments.
• Integrate AI components with vector databases, graph databases, internal applications, and other infrastructure tools—working alongside engineers who manage the underlying systems.
• Document model usage patterns, agent behaviors, experimental findings, workflow designs, and best practices for reproducibility and maintainability.
• Collaborate with cybersecurity and governance teams to ensure AI implementations adhere to required policies and safe‑use guidelines.

REQUIRED:

• Top Secret Cleared.
• Bachelor's Degree.
• Minimum 7-10 years of related experience.
• Ability to iteratively tune, evaluate, and validate AI workflows, including refining prompts, agent configurations, tool‑calling patterns, and retrieval strategies.
• Experience designing and running structured tests for AI behavior such as regression tests, scenario‑based evaluations, synthetic testing, and model comparisons.
• Skills in diagnosing and correcting AI system failures, including hallucinations, retrieval issues, or tool‑use errors, and implementing guardrails or workflow adjustments.
• Documents and maintains AI models, agent behaviors, experiments, and workflow designs.
• Proficient in data modeling and familiar with AWS Bedrock services.
• Proficiency in Python; familiarity with JavaScript or other languages beneficial.
• Comfortable working with CI/CD and Git-based development workflows.
• Experience integrating observability tools into AI application workflows (logging, metrics, traces).
• Experience with AI Agents & Workflow Integration (Advanced).
• Ex…