Software Engineer

Required Skills & Experience

-6–8+ years of software engineering experience, with a strong senior‑level mindset and ownership mentality.

-Strong experience with Python 3x in production environments.

-Proven experience building and operating production FastAPI or Flask APIs (secure, versioned, well‑documented).

-Hands‑on experience integrating AI/LLM services into real products (not just experimentation).

-Solid understanding of how LLMs work in practice and the components involved in interacting with them (prompts, responses, guardrails, quality controls).

-Cloud experience with GCP or AWS (Azure acceptable), including managed compute and messaging services.

-Experience with relational databases (Postgres/MySQL) and caching layers (Redis or equivalents).

-CI/CD experience (e.g., GitHub Actions, Cloud Build), containerization with Docker, and familiarity with IaC (Terraform a plus).

Nice to Have Skills & Experience

-Experience building AI frameworks or platforms that sit around LLMs (input validation, response evaluation, cost/quality optimization).

-Intermediate data engineering skills using Python and SQL.

-Security experience: OAuth/OIDC, JWTs, service‑to‑service auth, secrets management.

-Familiarity with data pipelines and schema evolution practices.

-Front‑end experience with React is a strong plus (potential full‑stack ownership).

Job Description

Insight Global is looking for a senior Software Engineer with a Python focus to join a leading client in Plano, TX. This role focuses on building, scaling, and owning backend frameworks and services that power AI‑driven products. You will not build or train LLM models, but you will design and productionize the systems, components, and workflows that interact with LLMs and AI services—ensuring quality, reliability, security, and performance at scale.

We are looking for a senior, self‑directed engineer who has worked on real AI products, understands how LLMs behave in production, and can independently take ownership of complex systems end‑to‑end.

What You’ll Do

-Design, build, and own scalable Python/FastAPI services and internal frameworks that integrate with LLMs and AI platforms.

-Develop AI‑enablement frameworks that manage prompt inputs, response validation, quality checks, retries, guardrails, and cost controls.

-Integrate third‑party AI providers (e.g., Gemini via Vertex AI, AWS Bedrock, OpenAI) using secure, observable, production‑ready patterns.

-Build both synchronous and event‑driven backends (REST APIs, webhooks, queues) with strong error handling and resiliency.

-Optimize latency, throughput, and cost through caching, rate limiting, retries, and circuit‑breaker patterns.

-Own services from development through production: testing, CI/CD, monitoring, runbooks, and operational readiness.

-Collaborate closely with product, data, and ML teams to translate AI product requirements into robust backend workflows and APIs.

-Act as a technical owner—asking intelligent questions, navigating ambiguity, and driving solutions rather than waiting for direction.

-Uphold security, privacy, and compliance standards (secrets management, OAuth/OIDC, PII handling).