Broad outline of the Role
As an AI Software Developer, you will design, develop, and own end‑to‑end AI solutions for Dark NOC, an AI‑driven automation platform for customer operations support. You will be responsible for full‑stack AI development, covering model integration, application logic, APIs, workflows, and production readiness.
In this role, you will work closely with the Project Manager to translate business and operational requirements into scalable, reliable, and automated AI capabilities. You will build and productionize solutions leveraging LLMs, NLP, RAG‑based systems, and automation workflows to enable proactive issue detection, intelligent troubleshooting, and autonomous operations.
You will take complete ownership of the development lifecycle from design and implementation to testing, deployment, and optimization, ensuring the Dark NOC platform delivers secure, cost‑efficient, measurable, and SLA‑aligned AI automation for enterprise customer operations.
Minimum Qualifications Experience
Bachelor's degree in engineering, 5–10 years of relevant experience.
Core Knowledge Skills
- Proficiency in Python programming.
- Strong experience developing AI‑driven automation solutions using LLMs/NLP (Llama, Mistral, Falcon, Claude Sonnet) and RAG‑based architectures.
- Hands‑on knowledge of LangChain / LlamaIndex; prompt engineering; function calling; embeddings, including prompt design, validation, and response quality evaluation.
- Experience integrating AI models using LLM function/tool calling APIs for automated decision‑making and actions.
- Strong programming skills in Python, Node.js, or building scalable APIs and services.
- Proficiency in Git for source control and collaborative development.
- Strong hands‑on experience with REST and gRPC APIs, including HTTP status codes, payload structures, rate limiting, retries, and error handling.
- ML tooling: scikit‑learn, transformers; experiment tracking (e.g., MLflow/Weights & Biases); model registry.
- MLOps/DevOps: Git, CI/CD (GitHub/GitLab/Azure DevOps), Docker, Kubernetes; API gateways.
- Observability: Prometheus, Grafana, ELK/EFK, Loki; log/metrics correlation; cost/latency dashboards.
- Security compliance: secrets management (Vault/Key Vault/SM), token hygiene, PII redaction, RBAC, audit logging.
- Hands‑on experience using Visual Studio Code (preferred for Python) and Visual Studio with Python workload, along with Git and Docker for local development and containerized builds, with active usage in both C#/.NET and Python development.
- Minimum 4–10 years of hands‑on development experience with MySQL or PostgreSQL.
Other Knowledge Skills
Ability to understand business goals and map to technical requirements.
Exposure toward working in the RFP cases.
Knowledge of creating HLD and LLD.
Good understanding of use cases and able to create solutions relating to the use cases.
Proficient with VS Code + Python FastAPI programming + SIP/VoIP (Asterisk/FreeSWITCH/Kamailio) + REST APIs + LLM (voice bot omnichannel CX integration), LINUX development.
Key Responsibilities
- End‑to‑End Solution Design Development – Translate business and operational requirements into architecture, user stories, and technical designs for Dark NOC features; build full‑stack AI capabilities: model integration, orchestration logic, APIs/services, and workflow automation.
- Model Integration Prompt Engineering – Integrate LLMs/NLU/ASR/TTS providers with robust adapters, retries, timeouts, and fallbacks; design and maintain prompts, system policies, and tool schemas; evaluate and refine prompts for accuracy and reliability; implement guardrails (policy enforcement, PII masking, safety filters) and quality evaluation.
- Data Engineering for Dark NOC – Build data ingestion and transformation pipelines for logs, alerts, tickets, and knowledge bases; maintain feature/knowledge freshness SLAs and data contracts with upstream systems; integrate with New Relic, ServiceNow, Email, chat, REST APIs for end‑to‑end automation.
- Testing & Quality Evaluations – Implement unit, integration, e2e tests, plus AI evaluations (groundedness, hallucination, toxicity); create offline and shadow/AB evaluations for prompts, models, and RAG changes before production rollout; define acceptance criteria with the Project Manager; maintain a robust regression suite.
- CI/CD Operations‑Ready Builds – Set up CI/CD pipelines with canary/blue‑green releases, automated rollbacks, and migration/versioning for prompts, models, and indexes; containerize services (Docker) and deploy to Kubernetes with observability hooks and resource limits; produce runbooks and operational toggles (feature flags, kill switches, fallback modes).
- Collaboration & Delivery Management – Work closely with the Project Manager on scope, estimations, milestones, and risk tracking; partner with platform, infra, and data teams to unblock dependencies and align environments and SLAs; provide clear documentation (designs, APIs, runbooks, evaluation results) and demo increments to stakeholders.
- Production Support (L3 Level) – Support pre‑prod validations and production rollouts; analyze incidents with traces/logs and drive code fixes; own root‑cause analysis for code/config issues and convert findings into tests, guardrails, and automation.