Profile — Sanjeev Kumar Singh

Summary

Production support and reliability engineer with 15 years operating mission-critical financial-services applications — troubleshooting complex production issues and improving monitoring, incident response and operational readiness. Currently Second Vice President / Application Support Consultant at Northern Trust. Founder-builder of Tracelane, an open-core LLM gateway and AI-agent observability platform, with hands-on depth in OpenTelemetry GenAI, guardrails, evaluation, distributed systems and automation.

Experience

Founder & Principal Engineer (part-time)

Tracelane · tracelane.dev

Mar 2026 — Present

Founded, architected and launched an open-core LLM gateway and AI-agent observability platform focused on reliability, governance and preventing agent failures before execution.
Built production observability across LLM calls, tool calls, browser actions, agent handoffs and MCP interactions using OpenTelemetry GenAI and ClickHouse-backed trace analytics.
Implemented guardrails, MCP failure-signature detection, cryptographic audit trails and policy controls for production agent workflows.
Shipped production-readiness engineering: eval-gated CI, provider failover, queue replay, blue-green deployment, rollback, fault-tolerance testing.
Built multi-tenant controls: SSO/RBAC, secure BYOK key management, tenant quotas.
Measured 4.6 ms p99 gateway overhead, 375 µs p99 inline guardrail dispatch, ~11,500 rows/sec single-node ingest.

Second Vice President, Application Support Consultant

Northern Trust

Oct 2021 — Present · London → Bengaluru

Lead L2 support for mission-critical institutional financial platforms across EMEA/APAC, maintaining 99% SLA uptime as senior escalation point for production incidents.
Manage and mentor 12+ specialists across 20+ global fund-servicing applications; hired and mentored 7 DevOps engineers through Kubernetes/containerization transformation.
Led the Bedrock monitoring initiative end-to-end: operational blind spots → requirements → engineering partnership → testing → production deployment.
Designed and executed annual EMEA/US disaster-recovery exercises aligned to RTO/RPO; coordinate 24/7 follow-the-sun operations.
Reduced recurring incidents by ~30% (trend analysis, automation, problem management) and manual operational work by ~30% (proactive alerting, certificate-lifecycle automation).
Partner with senior management and auditors on KPMG / SOC 2 Type II audits — architecture, security controls, roles, operational reporting.

Technology Lead, L2 Application Support

Northern Trust · via Infosys

2018 — 2021 · London

Managed and mentored 12+ specialists supporting 20+ global fund-servicing applications, owning service reliability, incident response and continuous improvement.
Led zero-downtime production upgrades and coordinated distributed support coverage for mission-critical applications.

Technology Analyst, Application Support

NatWest Group · via Infosys

2015 — 2017 · Chennai

24/7 production support for trade affirmation and confirmation platforms; resolved customer-impacting issues with live SQL fixes and workflow optimization.
Managed incident/change processes and regulatory reporting coordination via ServiceNow and JIRA.

Software Engineer, ETL Support & Enhancement

AIG · via Mphasis

2011 — 2014 · Chennai

Supported Oracle data-warehouse ETL workflows, PL/SQL development, SQL performance tuning and business-critical reporting for BFSI clients.

Technical skills

AI / LLM: LLM gateway architecture, multi-provider routing, OpenTelemetry GenAI, agent observability, guardrails, evaluation pipelines, MCP tooling
Reliability: Incident response, escalation management, RCA, monitoring & alerting, production readiness, DR/BCP, RTO/RPO, SLA ownership
Languages: Python, Rust (Axum/tokio), TypeScript, SQL/PL-SQL, Shell
Cloud & infra: AWS, Azure, Kubernetes, Docker, Cloudflare Workers, CI/CD, NATS JetStream, Kafka
Data: ClickHouse, PostgreSQL, Oracle, ServiceNow, JIRA
Security: SOC 2 Type II, SSO/RBAC, BYOK, mTLS/SPIFFE, cryptographic audit trails, SBOM

Education & certifications

B.E. Electronics & Communication — Anna University, Chennai · 2007 — 2011 · First Class with Distinction

ITIL V3 Foundation · Agile Kanban

Recognition

Multiple client appreciation awards at Infosys and Northern Trust · Quarterly Achiever and SPOT recognitions at Infosys · Mphasis Monthly Summit Award.