Artificial Intelligence Engineer

Total CollectR

Applied AI Engineer

This role is hands-on: youll prototype quickly, build production-grade systems, evaluate model quality, and collaborate closely with product, data, design, and domain experts.

What You’ll Do

• Build end-to-end LLM applications (RAG, agents, classifiers, summarizers).
• Design prompts, system instructions, and model interaction flows.
• Implement retrieval pipelines (embeddings, vector search, chunking, metadata filtering).
• Integrate AI models into backend services and product features.
• Select, tune, and manage models, embeddings, and data pipelines.
• Build eval suites for accuracy, safety, and reliability; run A/B tests and model benchmarks.
• Develop scalable, resilient inference services with caching, batching, and fallbacks.
• Deploy and monitor AI services with MLOps/Platform teams.
• Collaborate with PM, design, and domain experts to ship high-quality features.

What You Bring

• 3–5 years of experience

  in software engineering, applied ML, or AI product development.
• Strong software engineering background (Python, TypeScript/Node, etc.).
• Experience with LLMs (OpenAI, Anthropic, OSS) and RAG architectures.
• Familiarity with embeddings, vector DBs (FAISS, Pinecone, Weaviate).
• Knowledge of APIs, cloud infra (AWS/GCP/Azure), Docker, and production systems.
• Strong problem-solving and product-focused mindset.

Nice to Have

• Experience with agentic systems, tool-calling, or multi-step pipelines.
• Model fine-tuning (LoRA, supervised tuning).
• Data engineering/MLOps experience (Airflow, Dagster, CI/CD).
• Observability (OpenTelemetry) or safety frameworks.
• Experience building eval suites or working with labeled datasets.

Who You Are

Curious, fast-moving, and quality-driven. You think in terms of user value, enjoy ambiguity and love building practical AI solutions.

Success in This Role

Shipping impactful AI features, reducing hallucinations with structured evals and guardrails, scaling systems efficiently, collaborating across teams, and establishing best practices for AI development.