Senior AI Backend Engineer

Company: Coforge
Location: LATAM (Exclusive)
Mode: Remote
Experience: +7 YOE
Key Skills: Python, FastAPI, REST APIs, Distributed Systems, LLM Orchestration, AWS, Docker, CI/CD, AI Evaluation Frameworks, STT Pipelines

About the Role

Coforge is seeking a highly skilled Senior AI Backend Engineer (Job ID: 21736) to build and operate the production backend for a Voice-to-Action AI pipeline. This role involves designing scalable backend systems, developing AI evaluation frameworks, and ensuring the reliability of Speech-to-Text (STT) and LLM orchestration services within a distributed architecture.

Key Responsibilities

• Build and operate the production backend for a Voice-to-Action AI pipeline, including STT and LLM orchestration services.
• Design scalable and reliable backend systems within an existing distributed architecture.
• Develop instrumentation, evaluation, and regression frameworks for AI workflows and LLM-based systems.
• Define and monitor key quality metrics (e.g., transcription accuracy, normalization drift, edit rate, field-audio performance).
• Establish feedback loops and calibration practices to optimize non-deterministic AI systems in production.
• Evaluate and benchmark STT and LLM providers against internal performance metrics.
• Build and maintain scalable cloud-native services using AWS, Docker, and CI/CD pipelines.
• Collaborate with backend engineering teams to enhance operational excellence and platform scalability.
• Support the adoption of AI-assisted and agentic engineering workflows across the organization.
• Contribute to broader backend platform initiatives once the Voice-to-Action pipeline is production-ready.

Required Skills & Qualifications

• 7+ years of experience in backend engineering with strong expertise in Python.
• Hands-on experience with FastAPI or similar backend frameworks.
• Strong understanding of REST API development, service architecture, and distributed systems.
• Proven experience deploying and operating production systems on AWS, GCP, or Azure.
• Strong knowledge of Docker, CI/CD pipelines, cloud infrastructure, and operational best practices.
• Experience building and maintaining production-grade AI/LLM systems.
• Proven track record of implementing instrumentation, evaluation, regression testing, and monitoring for non-deterministic AI components.
• Strong analytical and problem-solving mindset with a focus on measurement and reliability.
• Ability to quickly learn new domains and adapt to evolving technologies.
• Experience working in fast-paced engineering environments with changing requirements.

Preferred Skills

• Deep experience with LLM orchestration frameworks and AI evaluation infrastructure.
• Experience with hosted LLM APIs (OpenAI, Anthropic, Bedrock, Vertex AI).
• Familiarity with STT/ASR providers (Whisper, Deepgram, AssemblyAI).
• Knowledge of MLOps and AI observability/monitoring tools.
• Experience with agentic coding workflows (Claude Code, Cursor).
• Backend experience in TypeScript or Node.js.
• Experience with mobile voice pipelines or audio processing systems.
• Bilingual or multilingual NLP experience.
• Strong technical leadership and mentorship capabilities.

About Coforge

At Coforge, we hire professionals based solely on their skills and do not discriminate based on age, disability, religion, gender, sexual orientation, socioeconomic status, or nationality.