AI Engineer| Remote | Full-time

Glynac.ai is building intelligent AI-powered systems that help organizations automate complex

workflows, discover actionable insights, and make better decisions from their data.

We are looking for an AI Engineer with 3+ years of experience who is passionate about building

production-grade AI systems. You will work across LLMs, AI agents, RAG, APIs, data pipelines,

evaluation, and observability to turn AI capabilities into reliable enterprise products.

What You’ll Do

• Design, build, and deploy LLM-powered applications and AI agents for real-world

enterprise use cases.

• Develop AI workflows using LLMs, RAG, tool calling, agent orchestration, and structured

outputs.

• Build integrations with internal and external APIs, data sources, and enterprise systems.

• Develop and maintain Python-based AI services and APIs using FastAPI or similar

frameworks.

• Build retrieval systems using vector databases, embeddings, reranking, and semantic

search.

• Design effective prompting strategies, context management, memory, and agent workflows.

• Build AI evaluation, testing, observability, and monitoring systems.

• Optimize AI applications for accuracy, latency, scalability, reliability, and cost.

• Work with product and engineering teams to translate business requirements into AI powered solutions.

• Investigate production issues and continuously improve AI system performance.

• Evaluate emerging AI technologies and identify opportunities to improve Glynac.ai

products.

Required Skills & Experience

• 3+ years of professional software engineering experience with meaningful experience in

AI/ML or Generative AI applications.

• Strong programming skills in Python.

• Hands-on experience building and deploying production LLM applications.

• Strong experience with LangChain, LangGraph, or similar AI/agent orchestration

frameworks.

• Strong understanding of RAG architectures, embeddings, vector databases, and retrieval

pipelines.

• Experience with LLM APIs such as OpenAI, Anthropic, Google, or equivalent models.

• Strong understanding of prompt engineering, tool/function calling, structured outputs, and

context management.

• Experience building backend services and REST APIs using FastAPI or similar

frameworks.

• Strong understanding of PostgreSQL/SQL and data management.

• Experience with Git, Docker, CI/CD, and cloud environments.

• Strong software engineering fundamentals including system design, testing, debugging,

and code quality.

• Ability to independently own technical problems from design → implementation →

deployment → monitoring.

Good to Have

• Experience building agentic AI systems and multi-agent workflows.

• Experience with Langfuse, OpenTelemetry, or similar AI observability platforms.

• Experience designing LLM evaluation frameworks and automated AI testing.

• Experience with AWS or other cloud platforms.

• Knowledge of Redis, Kafka, message queues, or event-driven architectures.

• Understanding of model evaluation, benchmarking, embeddings, reranking, fine-tuning,

and inference optimization.

• Experience integrating AI systems with enterprise SaaS platforms.

• Experience building multi-tenant enterprise applications.

• Understanding of AI security, data privacy, and responsible AI practices.

What We’re Looking For

We’re looking for an engineer who thinks beyond simply integrating an LLM API.

You should be comfortable solving questions such as:

• How do we make AI responses accurate and reliable?

• How do we evaluate AI systems automatically?

• How do we handle hallucinations and unexpected model behavior?

• How do we make AI workflows observable and debuggable?

• How do we optimize latency and inference costs?

• How do we design AI systems that can scale in production?

• How do we build systems that remain maintainable as models and requirements evolve?

You should be comfortable working in an environment where requirements can be ambiguous,

problems are complex, and engineers are expected to take ownership, move quickly, and build

production-ready solutions